Information Evolution Models With Random Leader Election Mechanism for Multi-Agent Cooperative Decision-Making

Linguistic fuzzy information evolution is crucial in understanding information exchange among agents. However, different agent weights may yield varying convergence results in the classic DeGroot model. Similarly, in the Hegselmann-Krause bounded confidence model (HK model), changing the confidence threshold values of agents can lead to differences in the final results. To address these limitations, this paper proposes three new models of linguistic fuzzy information dynamics: the per-round random leader election mechanism (PRRLEM)-based DeGroot model (PRRLEM-DeGroot), the PRRLEM-based homogeneous HK model (PRRLEM-HOHK), and the PRRLEM-based heterogeneous HK model (PRRLEM-HEHK). In these models, after each round of fuzzy information updates, an agent is randomly selected to act as a temporary leader with increased influence, and the leadership structure is reset after each update. This strategy enhances information sharing and improves decision-making by integrating evaluation information from multiple agents, which aligns with real-life scenarios (The leader is not unchanged). The Monte Carlo method is then employed to simulate the behavior of complex systems through repeated random tests, thereby obtaining confidence intervals for different types of fuzzy information. Subsequently, an improved golden rule representative value (GRRV) is proposed in fuzzy theory to rank these confidence intervals. A series of examples is employed to validate the effectiveness of the proposed models. The comparative analysis also shows that the proposed model increases the information entropy of the results from 0 (in the traditional model) to 2.234 bits. Note to Practitioners—This paper addresses challenges in group decision-making where agent influence and confidence thresholds impact consensus formation. Existing models often struggle with either fostering diverse outcomes or being overly sensitive to parameter changes. We propose a dynamic approach that introduces temporary leadership roles to enhance information sharing and prevent the formation of echo chambers. The model has been tested through simulations, demonstrating improved robustness and stability in decision-making. Potential applications include distributed sensor systems, social consensus modeling, and collaborative industrial processes. However, real-world implementations may require careful calibration to adapt to specific environments and system scales.